Nemotron 3.5 Lightning
Nemotron 3.5 Lightning is NVIDIA's small hybrid model (OpenMDW 1.1 licence, August 2026): 30B parameters with 3B active per token, combining state-space and mixture-of-experts layers for high throughput. NVIDIA describes it as a general-purpose reasoning and chat model for agent systems, chatbots, retrieval-augmented generation and instruction following. Supported languages: English, Spanish, French, German, Italian and Japanese; thinking can be switched on or off. It is fulfilled through global providers under our European contract, and requests go only to backends that do not retain prompts or completions.
model id: nemotron-3.5-lightning
from openai import OpenAI client = OpenAI( api_key="hb-...", base_url="https://api.heabsy.com/v1",) r = client.chat.completions.create( model="nemotron-3.5-lightning", messages=[{"role": "user", "content": "Hello"}],)print(r.choices[0].message.content)
curl https://api.heabsy.com/v1/chat/completions \ -H "Authorization: Bearer $HEABSY_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "nemotron-3.5-lightning", "messages": [{"role": "user", "content": "Hello"}] }'
import OpenAI from "openai"; const client = new OpenAI({ apiKey: process.env.HEABSY_API_KEY, baseURL: "https://api.heabsy.com/v1",}); const r = await client.chat.completions.create({ model: "nemotron-3.5-lightning", messages: [{ role: "user", content: "Hello" }],});console.log(r.choices[0].message.content);
Price list, updated 12 September 2026. No minimum spend, no subscription.
About the model
- Developer
- NVIDIA
- Released
- August 2026
- Licence
- OpenMDW-1.1
- Architecture
- mixture of experts · 30B parameters, 3B active per token
- Input
- text
- Reasoning
- switchable per request
- Languages named by the developer
- English, Spanish, French, German, Italian, Japanese
Source: the developer's model card, as of 17 September 2026.
Licence: what it means for your company
OpenMDW-1.1. OpenMDW 1.1, a permissive licence for model weights and data: per the developer's card you may use and modify the model and build commercial products on it without asking for permission.
A summary of the licence, not legal advice.
Technical details
- Context window
- 256K tokens
- Max output
- 65,536 tokens
- Throughput limit
- 200K tok/min
- Tokenizer
- Other
- Streaming
- yes
- Open weights
- nvidia/nemotron-3.5-lightning
- max_tokens
- 1 … 65536
- temperature
- 0 … 2
- top_p
- 0 … 1
- frequency_penalty
- -2 … 2
- presence_penalty
- -2 … 2
- stop
- array
- seed
- integer
This model is fulfilled through global providers under our European contract: one DPA with an EU company, one invoice for every model in the catalog, no US counterparty on your paperwork. Compute may run outside the EEA — if you need strict EEA-only processing, use our own-hardware model.
Questions about this model
›Where is Nemotron 3.5 Lightning computed?
Outside the EEA, through a global provider under our European contract. You get one DPA with an EU company and one invoice, but the compute itself does not run in the EEA — we state that instead of hiding it.
›Does Nemotron 3.5 Lightning store prompts and completions?
No. This model runs with zero data retention: request content is not written to durable storage and nothing is used for training.
›How large is the Nemotron 3.5 Lightning context window?
256K tokens, with up to 65,536 tokens of output.
›What does Nemotron 3.5 Lightning cost?
$0.12 per million input tokens and $0.31 per million output tokens. No minimum spend and no subscription; the same price list covers the API and the invoice.
›Is there a throughput limit on Nemotron 3.5 Lightning?
Yes, 200K tokens per minute. Higher limits are a question of volume, not of principle.
›Which languages does Nemotron 3.5 Lightning support?
The developer names English, Spanish, French, German, Italian, Japanese. Languages not on that list may still work, but they are not claimed — test on your own material first.
›Under which licence is Nemotron 3.5 Lightning released?
OpenMDW-1.1. OpenMDW 1.1, a permissive licence for model weights and data: per the developer's card you may use and modify the model and build commercial products on it without asking for permission.
›Can reasoning be switched off in Nemotron 3.5 Lightning?
Yes. Per the developer, thinking can be switched on or off for each request.
Compare with similar models
| Model | Developer | Parameters | Context | Licence | Input / 1M |
|---|---|---|---|---|---|
| Nemotron 3.5 Lightning | NVIDIA | 30B / 3B | 256K | OpenMDW-1.1 | $0.12 |
| Nemotron 3 Super 120B A12B | NVIDIA | 120B / 12B | 256K | NVIDIA Nemotron Open Model License | $0.13 |
| GLM-4.7-Flash | Z.ai | 30B / 3B | 195K | MIT | $0.09 |
| Gemma 4 31B | Google DeepMind | 30.7B | 256K | Apache-2.0 | $0.14 |
30 more models behind the same key and the same invoice.
Browse the catalog